Artificial intelligence is playing an increasingly important role in supporting decision-making, particularly in educational contexts, where it serves as a critical tool to assist teacher judgment and optimize instructional decisions. However, limited research has examined how different AI-assisted decision-making paradigms influence the Performance of human-AI collaboration, as well as the underlying psychological mechanisms and causal pathways. Therefore, this study investigated 59 pre-service teachers to examine how AI-assisted decision-making paradigms and human-AI consistency influenced their psychological states and task performance. Specifically, this study employed a two-factor mixed experimental design, with the AI-assisted decision-making paradigms as the between-subjects factor and human-AI consistency as the within-subjects factor. Data were analyzed using the Bayesian cumulative link mixed model and structural equation modeling. The results reveal that AI-assisted decision-making paradigms do not have a significant direct effect on task performance. However, when the moderating role of human-AI decision consistency is taken into account, the effect of AI-assisted decision-making paradigms on task performance can exert its influence indirectly through a sequential psychological pathway involving users’ confidence and their trust in the AI. Consistency between human and AI decisions not only significantly enhances users’ trust in AI, confidence, and task performance, but the proportion of consistent decisions also significantly moderates the impact of AI-assisted decision-making paradigms on users’ confidence levels. Notably, our findings indicate that users maintain a moderately level of trust in AI even when their decisions diverge from those of AI. In summary, this study highlights the mediating mechanism by which AI-assisted decision-making paradigms influence task performance through psychological states and identifies the moderating role of human-AI consistency in this pathway. These findings advance the theoretical understanding of human-AI interaction models in educational contexts and offer mechanistic insights to guide the optimization of instructional AI systems.

Large Language Models (LLMs) are increasingly being applied in education, showing significant potential in personalized instruction, student feedback, and intelligent tutoring. Generating hints for Math Word Problems (MWPs) has become a critical application, particularly in helping students understand problem-solving steps and logic. However, existing models struggle to provide pedagogically sound guidance that fosters learning without offering direct answers. To address this issue, we introduce TMATH, a dataset specifically designed to evaluate LLMs’ ability to generate high-quality hints for MWPs. TMATH contains diverse mathematical problems paired with carefully crafted, human-generated hints. To assess its impact, we fine-tuned a series of 7B-scale language models using TMATH. Our results, based on quantitative evaluations and expert assessments, show that while LLMs still face challenges in complex reasoning, the TMATH dataset significantly enhances their ability to generate more accurate and contextually appropriate educational hints.

As the demand for precision, efficiency, and low-cost solutions in educational classification tasks continues to grow, enhancing model performance has become a critical focus of research. While large language models excel in these tasks, their high cost and resource requirements limit widespread application. This study proposes a Knowledge-Enhanced Distillation (KED) method, utilizing ChatGPT-4, ChatGPT-4o, and Llama3 as teacher models, and three different sizes of BERT models as student models. The method was validated across three real-world educational datasets. The results demonstrate that the KED method significantly improves the accuracy and F1 scores of small models in educational text classification tasks, while also substantially reducing computational costs and resource consumption. Notably, the KED method shows exceptional performance in scenarios involving few-shot learning and class imbalance. The innovation of this study lies in applying the KED method to educational classification tasks, filling a gap in current research and highlighting its significant potential for practical application in educational contexts.

Faced with abundant online course resources, learners struggle to choose suitable materials. Learning resource recommendation algorithms can help address this. Rich online learning behavior data enables such recommendations. However, existing research only uses behavior events as learner features, ignoring event order i.e. Learning Behavior Patterns (LBPs). Also, only using click counts loses valuable information, hurting performance. We propose an algorithm leveraging online behavior sequences. First, extract sequences from logs and generate LBPs. Next, calculate Term Frequency Inverse Document Frequency (TF-IDF) values for each LBP as feature vectors. Cluster learners to improve efficiency. Finally, Calculate intra-cluster similarities for collaborative filtering recommendations. Experiments show over 30% precision, 9% recall, and 10% F1 improvements versus existing methods. Further ablation indicates learner clustering boosts time efficiency 3.75x without performance impact. Using TF-IDF values and tuning LBP length significantly improves performance. Overall, modeling orders via LBPs and better features like TF-IDF give major gains.